hangsiahong
20 verified skills
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
development
blast-radius-check
Use before modifying shared functions, core utilities, class definitions, or database schemas. Maps out all dependencies and referencing symbols to prevent unintended breakage in other files.
testing
receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
development
using-git-worktrees
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
tools
subagent-driven-development
Use when executing implementation plans with independent tasks in the current session
development
code-intelligence
Use when working on large, multi-service codebases where semantic search and global project context are needed to find relevant code or explain architecture.
development
self-critic
Autonomous adversarial critic agent that spawns in the background to challenge, question, and find flaws in the builder agent's work. Use when: (1) working on complex tasks where correctness matters, (2) building features that need a second opinion, (3) writing code that could have hidden assumptions, (4) any task where you want an independent devil's advocate reviewing your reasoning and output in real-time. Spawns a background critic with configurable harshness levels (paranoid/reasonable/chill) that injects non-blocking feedback.
development
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
development
dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies. Integrated with tmux-workflow for observability and session-distiller for context management.
testing
memory-maker
Use at the end of a session, milestone, or when closing a branch. Permanently records architectural decisions, "gotchas", and state changes to the long-term memory system so future agents don't repeat mistakes.
development
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
development
session-distiller
Automatically extracts, summarizes, and distills the current session context into a minimal, token-efficient 'Context Checkpoint'. Used to pass essential state to subagents or to restart a session without losing momentum. Solves the context-bloat problem by filtering noise and focusing on the 'What, Why, and What's Next'.
testing
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
development
tmux-workflow
Use when running multiple parallel agents, monitoring long-running background tasks, or requiring a multi-pane observability dashboard for parallel implementation plans.
data-ai
using-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
tools
verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
data-ai
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
development
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
testing
executing-plans
Use when you have a written implementation plan to execute in a separate session with review checkpoints
testing
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code
development